Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Representation for Clustering Via Prototype Scattering and Positive Sampling
Zhizhong Huang, Jie Chen, Junping Zhang, Hongming Shan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add prototype scattering loss (PSL) (ablation) | ProPos · CIFAR-10 | ACC: 87.9 -> 91.6 | Improved |
| add prototype scattering loss (PSL) (ablation) | ProPos · CIFAR-20 | ACC: 55.0 -> 57.8 | Improved |
| add positive sampling alignment (PSA) (ablation) | ProPos · CIFAR-10 | ACC: 90.3 -> 91.6 | Improved |
| add positive sampling alignment (PSA) (ablation) | ProPos · CIFAR-20 | ACC: 55.1 -> 57.8 | Improved |
| add PSL uniformity term (ablation) | ProPos · CIFAR-10 | ACC: 87.8 -> 91.6 | Improved |
| add PSL alignment term (ablation) | ProPos · CIFAR-10 | ACC: 92.1 -> 91.6 | No clear effect |
| add PSL alignment term (ablation) | ProPos · CIFAR-20 | ACC: 57.3 -> 57.8 | Improved |
| replace CC cluster head with PSL (ablation) | CC · CIFAR-10 | ACC: 74.6 -> 83.4 | Improved |
| integrate CC loss into BYOL (ablation) | BYOL · CIFAR-10 | ACC: 87.8 -> 86.3 | Hurt |
| integrate PCL loss into BYOL (ablation) | BYOL · CIFAR-10 | ACC: 87.8 -> 85.3 | Hurt |
| add PSL and PSA to BYOL on long-tailed data | BYOL · CIFAR-20-LT | ACC: 34.6 -> 39.0 | Improved |
| add PSL on top of PSA on long-tailed data (ablation) | ProPos w/o PSL · CIFAR-10-LT | ACC: 42.7 -> 43.9 | Improved |
Closest papers by meaning
- You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering (NeurIPS 2025 · similarity 0.88)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.86)
- Exploring a Principled Framework for Deep Subspace Clustering (ICLR 2025 · similarity 0.86)
- Decoupled Contrastive Multi-View Clustering with High-Order Random Walks (AAAI 2024 · similarity 0.86)
- From Logits to Hierarchies: Hierarchical Clustering made Simple (ICML 2025 · similarity 0.86)
- GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
